StressDream: Steering Video World Models for Robust Policy Evaluation and Improvement 事件

StressDream: Steering Video World Models for Robust Policy Evaluation and Improvement arXiv:2606.00267v1 Announce Type: new Abstract: Video world models (WMs) have shown promise for policy evaluation and improvement by imagining realistic future observations conditioned on ego-robot actions. While WMs can model distributions over futures, policy evaluation and improvement typically rely on nominal imaginations, which can miss high-impact outcomes of robot actions unless prohibitively many sampl